INDEX
Explanations
references to competitive sporting events and their related entities
New Auto-Interp
Negative Logits
ziel
-0.16
esar
-0.15
çĬ¬
-0.14
otland
-0.14
ζη
-0.14
.metro
-0.14
δο
-0.14
lew
-0.14
Äł
-0.14
umas
-0.14
POSITIVE LOGITS
gnore
0.15
ibus
0.15
cho
0.14
nero
0.14
ÅĤu
0.14
119
0.13
Terra
0.13
Trait
0.13
Terry
0.13
jet
0.13
Activations Density 0.015%